Abstract
Successive unfolding is a recently developed tech nique that appears to have advantages over traditional unfolding techniques. To assess its usefulness, succes sive, internal, and a type of external unfolding were compared with regard to the stimulus configurations recovered, the fit of the models as a whole, the fit of individual subjects, and each model's stability in a cross-validation sample. The data were obtained from judgments of similarity of and preference for occupa tional titles. Internal unfolding yielded degenerate so lutions and was dropped from subsequent analyses. External and successive unfolding yielded interpretable dimensions, but the nature of the dimensions uncov ered differed somewhat from one type of unfolding to the other. Both types of unfolding fit the data ade quately for the stimulus configuration, though succes sive unfolding appeared to fit better. The first two di mensions of both models were well reproduced in cross-validation samples. Dimensions beyond the sec ond were more easily cross-validated using external unfolding. Successive unfolding proved superior to ex ternal unfolding in representing preference data as in dicated by the fit of ideal points. Successive unfolding appears a viable method in unfolding research.
Get full access to this article
View all access options for this article.
